Instructions to use internlm/internlm2-1_8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use internlm/internlm2-1_8b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="internlm/internlm2-1_8b", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("internlm/internlm2-1_8b", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use internlm/internlm2-1_8b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "internlm/internlm2-1_8b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "internlm/internlm2-1_8b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/internlm/internlm2-1_8b
- SGLang
How to use internlm/internlm2-1_8b with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "internlm/internlm2-1_8b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "internlm/internlm2-1_8b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "internlm/internlm2-1_8b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "internlm/internlm2-1_8b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use internlm/internlm2-1_8b with Docker Model Runner:
docker model run hf.co/internlm/internlm2-1_8b
1.8b系列大海捞针的模型对比
#2
by chaochaoli - opened
"有效支持20万字超长上下文:模型在20万字长输入中几乎完美地实现长文“大海捞针”,而且在 LongBench 和 L-Eval 等长文任务中的表现也达到开源模型中的领先水平。"====>
如model card所描述,1.8b模型在20w字的大海捞针中几乎完美实现,我想了解下这块有详细的评测结果吗?还有就是base、sft和chat版本在这块能力上的差异是怎么样的?哪个会比较好?感谢。祝好。
internlm2 好像没有paper吧,只能社区自己复现